Quick/Comparisons
26 | Gaming | 66 |
39 | Workstation | 66 |
29 | AI/ML |
Compare with something else?
Compare Apple M2 Max with another →57 |
76 | Energy Efficiency | 44 |
38 | Quick Comparison Final Score | 64 |
| — | Graphics Processor | AD104 |
| 4864 | Cores | 7680 |
| 304 / 152 | TMUs / ROPs | 240 / 80 |
| 1777.05 | Blender GPU | 6639.7 |
| — | Forza Horizon 5 | 141 |
| — | The Witcher 3 | 182 |
| — | Counter-Strike 2 | 216 |
| — | Far Cry 6 | 148 |
| — | Hogwarts Legacy | 114 |
| — | Call of Duty | 171 |
| — | Ghost of Tsushima | 106 |
| — | Cyberpunk 2077 | 142 |
| — | Tomb Raider | 245 |
| — | Average FPS | 163 |
| — | 1080p High | 194 |
| — | 1080p Ultra | 163 |
| — | 1440p Ultra | 128 |
| — | 4K Ultra | 75 |
| — | Margin of Error | Low |
| 86936 | GB6 Compute Score | 219163 |
| 149 img/sec | Background Blur | 371.2 img/sec |
| 98.1 img/sec | Face Detection | 235 img/sec |
| 3.8 Gpixels/sec | Horizon Detection | 7.51 Gpixels/sec |
| 6.88 Gpixels/sec | Edge Detection | 10.6 Gpixels/sec |
| 4.44 Gpixels/sec | Gaussian Blur | 12.4 Gpixels/sec |
| 0.73 Gpixels/sec | Feature Matching | 2.03 Gpixels/sec |
| 264.9 Gpixels/sec | Stereo Matching | 1120 Gpixels/sec |
| 11144.2 FPS | Particle Physics | 30420.2 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 31568 |
| — | G2D Mark | 1209 |
| — | DirectX 11 | 288 FPS |
| — | DirectX 12 | 116 FPS |
| — | GPU Compute | 18221 Ops/s |
| 15005 | GB6 ML Single Precision | 32405 |
| 16456 | GB6 ML Half Precision | 48989 |
| 15418 | GB6 ML Quantized | 24894 |
| 6657 | Image Classification (SP) | 12496 |
| 13854 | Image Segmentation (HP) | 33378 |
| 18642 | Image Super Resolution (Q) | 37180 |
| 27965 | Face Detection (HP) | 62919 |
| 83144 | Pose Estimation (Q) | 171125 |
| 2377 | Text Classification (SP) | 3630 |
| 2052 | Machine Translation (HP) | 6420 |
| 6495 | Object Detection (SP) | 15804 |
| 31105 | Depth Estimation (Q) | 58647 |
| 135686 | Style Transfer (SP) | 331379 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 212 GPixel/s | Pixel Fill Rate | 209 GPixel/s |
| 425 GTexel/s | Texture Fill Rate | 626 GTexel/s |
| 13.6 TFLOPS | FLOPS (FP32) | 40.1 TFLOPS |
| System Shared | Memory Type | GDDR6X |
| — | Memory Size | 12 GB |
| 6400 MHz | Memory Clock | 1313 MHz |
| 12800 Mbps | Effective Memory Speed | 21000 Mbps |
| 512-bit | Bus | 192-bit |
| No | ECC | No |
| 409.6 GB/s | Memory Bandwidth | 504 GB/s |
| Custom | Interface | PCIe 4.0 x16 |
| 70 W | TGP | 285 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 5 nm |
| — | Die Size | 294 mm² |
| 52 billion | Transistor Count | 35 billion |
| — | Transistor Density | 119.05 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.3 |
| — | OpenGL | 4.6 |
| — | OpenCL | 3 |
| — | CUDA | 8.9 |
| No | Ray Tracing | Yes |
| No | DLSS | DLSS 3 |
| — | DisplayPort | 1.4a |
| Apple | Vendor | Nvidia |
| Integrated | Build | Discrete |
| January 17, 2023 | Released | January 3, 2023 |
| Laptop | Case | Desktop |
| Professional | Purpose | Gaming |
| High-end | Segment | Mid-range |
| Apple M GPU | Architecture | Ada Lovelace |
| — | GPU Codename | AD104 |
| — | Recommended CPU | -Intel Core i7 14700Kor above |
| 9413 | Steel Nomad Lite Score | 23618 |
| — | Time Spy | 22751 |
| 30427 | Solar Bay | 108422 |
| — | Port Royal | 13994 |
| — | Fire Strike | 53484 |
| 24969 | Wild Life Extreme | 45397 |
| — | Night Raid | 171258 |
| 450 MHz | Base Clock | 2310 MHz |
| 1398 MHz | Boost Clock | 2610 MHz |
| 4864 | Shading Units | 7680 |
| 304 | Texture Mapping Units (TMUs) | 240 |
| 152 | Render Output Units (ROPs) | 80 |
| 608 | Compute Units (Pipelines) | 60 |
| — | Tensor Cores | 240 |
| — | Ray-tracing Cores | 60 |
| — | L1 Cache | 128KB per cluster |
| — | L2 Cache | 48MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |